© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 128878
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    levision
    -0.08
    ajaran
    -0.07
    abh
    -0.07
     kola
    -0.07
    寿
    -0.07
     lesbi
    -0.07
    ÏĢει
    -0.07
    æłı
    -0.07
     cih
    -0.07
    _SECTION
    -0.07
    POSITIVE LOGITS
    ungi
    0.07
    organ
    0.06
    istributed
    0.06
    Circular
    0.06
     Spiral
    0.06
     caucus
    0.06
    à¤Ĥश
    0.06
     lots
    0.06
    gmail
    0.05
     distributed
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.